Ning Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ning Zhang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Fan Ouyang
College of Education, Zhejiang University, Hangzhou, Zhejiang, China
5 shared publications Xianping Bai
College of Education, Zhejiang University, Hangzhou, China
2 shared publications- Dongyang Gao
College of Information Engineering (Artificial Intelligence College), Yangzhou University, Yangzhou, China
1 shared publication - Eng Eng Ng
The Institute for Pedagogical Innovation, Research and Excellence (InsPIRE), Nanyang Technological University
1 shared publication - Guo Su
National Institute of Education, Nanyang Technological University
1 shared publication Jia Chen
School of Educational Information Technology, Central China Normal University, Wuhan, China
1 shared publication
Latest Publications
- Open Access
- 30 March 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (7) , 3338
Toward Sustainable Education: Generative AI-Powered Argument Mining in Student Writing
As critical elements in argumentative writing, argument components and strategies significantly influence argument quality. However, the existing research lacks an in-depth exploration of how students construct and utilize these elements in argumentative writing. This study first evaluates the performance of leading large language models (LLMs) in identifying argument components and strategies using three approaches: single-task learning (STL), chain-of-thought (CoT), and multi-task learning (MTL). With the aid of learning analytics methods (Epistemic Network Analysis (ENA) and two-mode network), the study further reveals the intrinsic mechanisms linking argument components, strategies, and writing quality. Specifically, the research trains and evaluates LLMs on 226 argumentative essays, encompassing 4726 components and 4837 strategies. Compared to basic STL, the CoT and MTL methods significantly improve LLMs’ performance in both tasks. Moreover, learning analytics indicate that high-quality essays possess rich and complex logical relations, presenting multidimensional and multi-layered reasoning structures, whereas low-quality essays predominantly rely on simple and repetitive connections, lacking deeper logical support. These findings have significant implications for the automated analysis of argumentative writing and the sustainable development of education, not only providing valuable insights for educators in argumentation instruction but also contributing to the systematic enhancement of students’ argumentative abilities and critical thinking.
- 30 March 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (7) , 3338
Open AccessToward Sustainable Education: Generative AI-Powered Argument Mining in Student Writing
As critical elements in argumentative writing, argument components and strategies significantly influence argument quality. However, the existing research lacks an in-depth exploration of how students construct and utilize these elements in argumentative writing. This study first evaluates the performance of leading large language models (LLMs) in identifying argument components and strategies using three approaches: single-task learning (STL), chain-of-thought (CoT), and multi-task learning (MTL). With the aid of learning analytics methods (Epistemic Network Analysis (ENA) and two-mode network), the study further reveals the intrinsic mechanisms linking argument components, strategies, and writing quality. Specifically, the research trains and evaluates LLMs on 226 argumentative essays, encompassing 4726 components and 4837 strategies. Compared to basic STL, the CoT and MTL methods significantly improve LLMs’ performance in both tasks. Moreover, learning analytics indicate that high-quality essays possess rich and complex logical relations, presenting multidimensional and multi-layered reasoning structures, whereas low-quality essays predominantly rely on simple and repetitive connections, lacking deeper logical support. These findings have significant implications for the automated analysis of argumentative writing and the sustainable development of education, not only providing valuable insights for educators in argumentation instruction but also contributing to the systematic enhancement of students’ argumentative abilities and critical thinking.
- 6 March 2026
- Published by Springer Nature in Educational Technology Research and Development
- Vol. 74 (3) , 1775-1800
The implementation of a group knowledge awareness tool to promote collaborative discussions in China’s higher education
- 6 March 2026
- Published by Springer Nature in Educational Technology Research and Development
- Vol. 74 (3) , 1775-1800
The implementation of a group knowledge awareness tool to promote collaborative discussions in China’s higher education
- 18 June 2025
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (16) , 22521-22546
The effects of online collaborative environments and scaffoldings on student engagement in collaborative problem-solving process
- 18 June 2025
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (16) , 22521-22546
The effects of online collaborative environments and scaffoldings on student engagement in collaborative problem-solving process
- 17 February 2025
- Published by Elsevier in Neurocomputing
- Vol. 628, 129683
A spatio-frequency cross fusion model for deepfake detection and segmentation
- 17 February 2025
- Published by Elsevier in Neurocomputing
- Vol. 628, 129683
A spatio-frequency cross fusion model for deepfake detection and segmentation
- 10 December 2024
- Published by Taylor & Francis in Technology, Pedagogy and Education
- Vol. 34 (3) , 275-295
The use and effect of cognitive scaffoldings on facilitating collaborative discussion-supported writing
- 10 December 2024
- Published by Taylor & Francis in Technology, Pedagogy and Education
- Vol. 34 (3) , 275-295
The use and effect of cognitive scaffoldings on facilitating collaborative discussion-supported writing
- 25 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Learning Technologies
- Vol. 17, 2173-2185
Comparing the Effects of Instructor Manual Feedback and ChatGPT Intelligent Feedback on Collaborative Programming in China's Higher Education
Artificial General Intelligence (AGI) has gained increasing global attention as the field of large language models undergoes rapid development. Due to its human-like cognitive abilities, the AGI system has great potential to help instructors provide detailed, comprehensive, and individualized feedback to students throughout the educational process. ChatGPT, as a preliminary version of the AGI system, has the potential to improve programming education. In programming, students often have difficulties in writing codes and debugging errors, whereas ChatGPT can provide intelligent feedback to support students' programming learning process. This research implemented intelligent feedback generated by ChatGPT to facilitate collaborative programming among student groups and further compared the effects of ChatGPT with instructors' manual feedback on programming. This research employed a variety of learning analytics methods to analyze students' computer programming performances, cognitive and regulation discourses, and programming behaviors. Results indicated that no substantial differences were identified in students' programming knowledge acquisition and group-level programming product quality when both instructor manual feedback and ChatGPT intelligent feedback were provided. ChatGPT intelligent feedback facilitated students' regulation-oriented collaborative programming, while instructor manual feedback facilitated cognition-oriented collaborative discussions during programming. Compared to the instructor manual feedback, ChatGPT intelligent feedback was perceived by students as having more obvious strengths as well as weaknesses. Drawing from the results, this research offered pedagogical and analytical insights to enhance the integration of ChatGPT into programming education at the higher education context. This research also provided a new perspective on facilitating collaborative learning experiences among students, instructors, and the AGI system.
- 25 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Learning Technologies
- Vol. 17, 2173-2185
Comparing the Effects of Instructor Manual Feedback and ChatGPT Intelligent Feedback on Collaborative Programming in China's Higher Education
Artificial General Intelligence (AGI) has gained increasing global attention as the field of large language models undergoes rapid development. Due to its human-like cognitive abilities, the AGI system has great potential to help instructors provide detailed, comprehensive, and individualized feedback to students throughout the educational process. ChatGPT, as a preliminary version of the AGI system, has the potential to improve programming education. In programming, students often have difficulties in writing codes and debugging errors, whereas ChatGPT can provide intelligent feedback to support students' programming learning process. This research implemented intelligent feedback generated by ChatGPT to facilitate collaborative programming among student groups and further compared the effects of ChatGPT with instructors' manual feedback on programming. This research employed a variety of learning analytics methods to analyze students' computer programming performances, cognitive and regulation discourses, and programming behaviors. Results indicated that no substantial differences were identified in students' programming knowledge acquisition and group-level programming product quality when both instructor manual feedback and ChatGPT intelligent feedback were provided. ChatGPT intelligent feedback facilitated students' regulation-oriented collaborative programming, while instructor manual feedback facilitated cognition-oriented collaborative discussions during programming. Compared to the instructor manual feedback, ChatGPT intelligent feedback was perceived by students as having more obvious strengths as well as weaknesses. Drawing from the results, this research offered pedagogical and analytical insights to enhance the integration of ChatGPT into programming education at the higher education context. This research also provided a new perspective on facilitating collaborative learning experiences among students, instructors, and the AGI system.
- 16 September 2024
- Published by Taylor & Francis in Assessment & Evaluation in Higher Education
- Vol. 50 (3) , 351-365
The influence of peer feed-back and peer feed-forward on international students’ L2 writing in China’s higher education
- 16 September 2024
- Published by Taylor & Francis in Assessment & Evaluation in Higher Education
- Vol. 50 (3) , 351-365
The influence of peer feed-back and peer feed-forward on international students’ L2 writing in China’s higher education
- 5 August 2021
- Published by SAGE Publications in Journal of Educational Computing Research
- Vol. 60 (1) , 132-169
Exploring the Relationship Between Social Interaction, Cognitive Processing and Learning Achievements in a MOOC Discussion Forum
In the field of learning analytics, mining the regularities of social interaction and cognitive processing have drawn increasing attention. Nevertheless, in MOOCs, there is a lack of investigations on the combination of social and cognitive behavioral patterns. To fill in this gap, this study aimed to uncover the relationship between social interaction, cognitive processing, and learning achievements in a MOOC discussion forum. Specifically, we collected the 3925 participants’ forum data throughout 16 weeks. Social network analysis and epistemic network analysis were jointly adopted to investigate differences in social interaction, cognitive processing between two achievement groups, and the differences in cognitive processing networks between two types of communities. Finally, moderation analysis was employed to examine the moderating effect of community types between cognitive processing and learning achievements. Results indicated that: (1) the high- and low-achieving groups presented significant differences in terms of degree, betweenness, and eigenvector centrality; (2) the stronger cognitive connections were found within the high-achieving group and the instructor-led community; (3) the cognitive processing indicators including insight, discrepancy, and tentative were significantly negative predictors of learning achievements, whereas inhibition and exclusive were significantly positive predictors; (4) the community type moderated the relationship between cognitive processing and learning achievements.
- 5 August 2021
- Published by SAGE Publications in Journal of Educational Computing Research
- Vol. 60 (1) , 132-169
Exploring the Relationship Between Social Interaction, Cognitive Processing and Learning Achievements in a MOOC Discussion Forum
In the field of learning analytics, mining the regularities of social interaction and cognitive processing have drawn increasing attention. Nevertheless, in MOOCs, there is a lack of investigations on the combination of social and cognitive behavioral patterns. To fill in this gap, this study aimed to uncover the relationship between social interaction, cognitive processing, and learning achievements in a MOOC discussion forum. Specifically, we collected the 3925 participants’ forum data throughout 16 weeks. Social network analysis and epistemic network analysis were jointly adopted to investigate differences in social interaction, cognitive processing between two achievement groups, and the differences in cognitive processing networks between two types of communities. Finally, moderation analysis was employed to examine the moderating effect of community types between cognitive processing and learning achievements. Results indicated that: (1) the high- and low-achieving groups presented significant differences in terms of degree, betweenness, and eigenvector centrality; (2) the stronger cognitive connections were found within the high-achieving group and the instructor-led community; (3) the cognitive processing indicators including insight, discrepancy, and tentative were significantly negative predictors of learning achievements, whereas inhibition and exclusive were significantly positive predictors; (4) the community type moderated the relationship between cognitive processing and learning achievements.